Artificial Neural Networks for Detection of Malaria in RBCs. Purnima Pandit1, A. Anand2
|
|
- Shannon Shaw
- 6 years ago
- Views:
Transcription
1 Artificial Neural Networks for Detection of Malaria in RBCs Purnima Pandit1 A Anand Department of Applied Mathematics1 Department of Applied Physics The Maharaja Sayajirao University of Baroda purnimapandit-appmath@msubarodaacin ABSTRACT: Malaria is one of the most common diseases caused by mosquitoes and is a great public health problem worldwide Currently for malaria diagnosis the standard technique is microscopic examination of a stained blood film We propose use of Artificial Neural Networks (ANN) for the diagnosis of the disease in the red blood cell For this purpose features / parameters are computed from the data obtained by the digital holographic images of the blood cells and is given as input to ANN which classifies the cell as the infected one or otherwise Keywords: ANN classification Malaria RBC Introduction Malaria is an ancient disease present majorly in the tropical countries having a huge social economic and health burden In recent times as a result of climatic changes due to global warming it is predicted to have unexpected effects on Malaria Both increase and fluctuation in temperature affects the vector and parasite life cycle An efficient diagnostics is essential for the proper medication and cure Major clinical diagnostics to identify RBCs affected by malaria is based on microscopic inspection of blood smears treated with reagents which stains the malarial parasite A technician visually inspects these smears to identify malariainfected red blood cells (RBCs) In developing countries visual identification of malarial RBCs may become inefficient due to lack of sufficiently trained technicians and poor-quality microscopes and regents During such hematologic disorder the changes occur in the structure and viscoelastic properties of individual RBCs So studying their physical properties can thus contribute greatly to the understanding and possible discovery of new treatments for such diseases Thus new advanced mathematical computing techniques are valuable for determining and distinguishing between the healthy and diseased RBCs In [1] Anand and at el have used correlation technique on the images obtained from DHIM to discriminate the malarial cells from the healthy ones An efficient computational techniques based on the 3-D images produced by digital holographic interferometric microscopy (DHIM) [6] to automatically discriminate between malarial and healthy RBCs can be very beneficial It will be advantageous if such DHIM capturing instruments are portable and easy to use We propose the technique to distinguish the malaria infected RBCs from the healthy ones using Artificial Neural Network (ANN) based on its physical/statistical features that are extracted from the images obtained from Digital Holographic Interferometric Microscope (DHM) Artificial Neural Network (ANN) for malaria diagnosis is one time trained intelligent program which is easy to use portable low cost and make malaria diagnosis more rapid and accurate
2 DIGITAL HOLOGRAPHIC INTERFEROMETRIC MICROSCOPY A hologram is the photographically or otherwise recorded interference pattern between a wave field scattered from the object and a coherent background called the reference wave The digital holographic interferometric microscopy comparisons of phases at the image plane obtained from the recorded holograms with the object present and with just the background provides object phase information This can be converted into thickness information of cells Then efficient computational techniques will be applied on the 3-D images produced by DHM for micro objects to automatically discriminate between malarial and healthy RBCs Dennis Gabor invented holography in 1948 as a method for recording and reconstructing the amplitude and phase of a wavefield The word holography is derived from the Greek words holos meaning whole or entire and graphein meaning to write A hologram is the photographically or otherwise recorded interference pattern between a wave field scattered from the object and a coherent background called the reference wave 31 Digital Hologram The general set-up for recording off-axis holograms is shown in figure 1 Light with sufficient coherence length is split into two partial waves by a beam splitter (BS) One wave illuminates the object is scattered and reflected to the recording medium eg a photographic plate The second wave called the reference wave illuminates the plate directly Both waves are interfering The interference pattern is recorded eg by chemical development of the photographic plate The recorded interference pattern is called a hologram Fig 1: Hologram Recording The original object wave is reconstructed by illuminating the hologram with the reference wave figure An observer sees a virtual image which is indistinguishable from the image of the original object The reconstructed image exhibits all the effects of perspective and depth of focus
3 Fig : Hologram reconstruction The holographic process is described mathematically as follows: ( ) ( ) exp phase ( ) (1) Equation (1) the complex amplitude of the object wave with real amplitude o and and ( ) ( ) ( ( )) () Equation () gives the complex amplitude of the reference wave with real amplitude r and phase Both waves interfere at the surface of the recording medium The intensity is calculated by ( ) ( ) ( ) ( ) ( ) ( ( ) ( )) R(x y) (x y) O(x y) (x y) O(x y) (x y) R(x y) (x y) where * denotes the conjugate complex The amplitude transmission h(x y) of the developed photographic plate (or any other recording media) is proportional to I(x y) that is h(x y) ℎ β I(x y) where β is a constant is the exposure time and ℎ is the amplitude transmission of the unexposed plate h(x y) is also called the hologram function In digital holography using charge-coupled device detector CCDs as recording medium ℎ can be neglected For hologram reconstruction the amplitude transmission has to be multiplied with the complex amplitude of the reconstruction (reference) wave: R(x y)h(x y) [ℎ β ( )]R(x y) β O(x y) β (x y) (x y)
4 The first term on the right side of this equation is the reference wave multiplied by a factor It represents the undiffracted wave passing through the hologram (zero diffraction order) The second term is the reconstructed object wave forming the virtual image The factor β only influences the brightness of the image The third term produces a distorted real image of the object For off-axis holography the virtual image the real image and the undiffracted wave are spatially separated 311 Recording in Digital holography In a set-up for digital recording of off-axis holograms is shown in figure 3 A plane reference wave and the wave reflected from the object are interfering at the surface of a CCD The resulting hologram is electronically recorded and stored The object is in general a threedimensional body with diffusely reflecting surface located at a distance d from the CCD Fig3: Digital holography: (a) recording (b) reconstruction In optical reconstruction the virtual image appears at the position of the original object and the real image is formed also at a distance d but in the opposite direction from the CCD see figure 3(b) The diffraction of a light wave at an aperture (in this case a hologram) which is fastened perpendicular to the incoming beam is described by the Fresnel Kirchhoff integral with ( ) ℎ( ) ( ) ( ( ) ( ) ) (3) (4) where ρ is the distance between a point in the hologram plane and a point in the reconstruction plane see figure 4 The angle θ is also defined in figure 4 The diffraction pattern is calculated at a distance d behind the CCD plane which means it reconstructs the complex amplitude in the plane of the real image
5 Equation (3) is the basis for numerical hologram reconstruction Because the reconstructed wave field (ξ η) is a complex function both the intensity as well as the phase can be calculated This is in contrast to the case of optical hologram reconstruction in which only the intensity is made visible Fig 4: Coordinate system The set-up of figure 4 is often used in digital holography because a plane wave propagating perpendicularly to the surface of the CCD can be easily arranged in the laboratory Another advantage is that for this geometry the reconstructed real image has no geometrical distortions 31 Reconstruction by the Fresnel transformation For x and y values as well as for ξ and η values which are small compared to the distance d between the reconstruction plane and the CCD expression (4) can be replaced by the first terms of the Taylor series: ( ) ( ) 1 [( ) ( ) ] 8 ( ) ( ) 1 with the additional approximation By replacing the dominator in (3) by ( ) exp exp ( the following expression results: ( )ℎ( ) )(( ) ( ) ) If we carry out the multiplications in the argument of the exponential under the integral we get
6 ( ) exp exp exp ) ( ( )ℎ( ) exp ( ) ( ) This equation is called the Fresnel approximation or Fresnel transformation It enables reconstruction of the wave field in a plane behind the hologram in this case in the plane of the real image The intensity is calculated by squaring The phase is calculated by ( ) ( ) ( ) [ ( )] [ ( )] where Re denotes the real part and Im the imaginary part These phase values are used for further processing of the DHMI of the RBCs Artificial Neural Networks Artificial Neural Networks (ANN) are massively parallel distributed processing systems representing a computational technology built on the analogy to the human information processing system They are massively connected networks of simple processing elements called neurons They have a natural propensity to learn and save the knowledge to make it available for use ANNs can be used for classification pattern recognition and function approximation It is an information processing system consisting of large number of interconnected processing units It works in a way our nervous system processes the information It is basically a dense interconnection of simple non-linear computational elements It has been successfully applied to problems involving pattern classification function approximation regression prediction and others The biological aspects of neural networks were modeled by McCullough and Pitts in 1943 This model exhibits all the properties of neural elements like excitation potential thresholds for neuron firing and non-linear amplification which compresses the strong input signal Various kinds of Neural Networks are used for different purpose Single-layer Perceptron Multi-layer Perceptron Hopfield recurrent networks Kohonnen self-organizing networks Radial Basis Function Networks Support Vector Machines and Extreme Learning Machines are most common amongst them The fundamental element of neural network is neuron It is an operator which maps ℝ ℝ and it is explicitly described by the equation
7 Here [ ] is an input vector (5) is the weight vector to the neuron and is the bias : ℝ ( 11) is a monotonic continuous function such as ℎ( ) or ( ) Such neurons are interconnected to form a network Amongst various activation functions the sigmoid activation function is more useful since it is continuous and differentiable The simple neural network is as shown in Fig 5 Fig 5: Feed forward Neural Network The Networks are categorized into mainly two categories: Feed Forward and Recurrent The learning algorithms are categorized in three types: supervised learning unsupervised learning and reinforced learning We have used multi-layer network Radial Basis Function Network which is a supervised learning algorithm Learning (or Training) is a process by which a network adapts changes by adjusting its changeable parameters ie weights They change in such a way that there is an association between set of inputs and desired outputs In Artificial Neural Networks The general rule for weight updating is Δ Here is weight in ( 1) iteration is the weight in iteration and is change in weight in step which can be determined using different algorithms ANN plays a primary role in contemporary artificial intelligence and machine learning The use of ANN in function approximation resulted from the following facts: (i) Cybenko and Hornik proved that the multi-layered Neural Network is universal approximator It can approximate any continuous function defined on compact set
8 (ii) The Back-propagation algorithm used for the training of the feed-forward Neural Networks with the hidden layers The Multi-layer feed forward network (MFFN) trained with Back Propagation Rule is one of the most important neural network model In the real practical situations when there is the lack of the mathematical model for the system the ANN can be trained with the help of InputOutput pairs without fitting any kind of model to the system The fundamental element of neural network is neuron We can refer to neuron as an operator which maps ℝ ℝ and is explicitly described by the equation (6) [ Γ (6) ] is input vector is weight vector to the neuron and w0 is the bias Γ( ) is a monotone continuous function Γ: ℝ ( 11) (eg ℎ( ) or ( )) Such neurons are interconnected to form a network Here w11 x1 x y1 x3 ym wln xn Input Layer Hidden Layer Output Layer Fig 6: A Multi Layered Feed-Forward Network In the Feed-forward network neurons are organized in layers ℎ 0 1 It is common practice to refer to the layer ℎ 0 as the input layer and ℎ as the output layer and to all other as hidden layers A neuron at layer ℎ receives its inputs only from neurons in the ℎ 1 layer The output of the element in the layer ℎ is given by Γ Here at the ℎ [ (7) ] is the weight vector associated with layer Such a family of networks with neurons at the neuron layer will be denoted by
9 The general learning rule for weight updating is ( 1) ( ) Δ ( ) where ( 1) is weight in ( 1) step ( ) is weight in ( ) step and ( ) is change in weight in ( ) step The change in weight for supervised delta rule is given by (8) The training in the Feed-forward type Multilayered neural network is done using backpropagation algorithm Back-propagation algorithm is an extension of delta rule for training for multilayer feed-forward networks Experimental Work We have the holographic image data for 48 RBC which are processed and then various features are obtained in following manner The phase data for the cells are obtained in gray scale to which thresholding or masking is done for the selection of portion of the image to work with The images obtained after converting it into grey scale for image of edge for different mask values 08 and 03 is shown in following figures: For Mask value 08 For Mask value 030 (a) (b) Fig 7: Image obtained after converting to black and white (a) (b) Fig 8: Image obtained after converting into binary to find area of RBC
10 (b) (a) Fig 9: Image obtained after detecting edges to find perimeter of RBC Once the portion of RBC image was selected the parameters were calculated for it like taking average of the phase of the image standard deviation and coefficient of variation To find the area we count the number of pixels selected for processing and the border pixels to obtain the perimeter Circularity is calculated using the formula c 4 A p Ideally healthy RBC is doughnut shaped and infected RBC becomes spherical due to growth of parasites within the RBC In our work the detection of healthy and infected RBC is done using six parameters Table 1 and Table shows such calculated values of six parameters: area perimeter circularity mean standard deviation and covariance These parameters were obtained using holographic images of 4 healthy RBC and 4 infected RBC Table 1: Parameter values for Healthy cells Table : Parameter values for Malaria infected cells
11 The six parameters obtained after preprocessing on holographic images are used as inputs for the detection of malaria infected and healthy cells to the Artificial Neural Network (ANN) The outputs of ANN are binary bipolar -1 stands for healthy and 1 stands for infected RBC MATLAB is used to create Feed-forward neural network The training was done using Back-propagation We had 48 patter10s consisting of 4 healthy and 4 malarial cells out of which 5 healthy and 5 malarial random patterns are kept for testing and remaining 38 patterns are used for training purpose We considered an ANN with architecture this network got trained in 10 iterations as shown in Figure 10 the error convergence and the state performance as shown in Figure 11 Fig 10: Trained ANN Window
12 Fig 11: Training Performance and Training state This trained network is the tested for the remaining testing patterns The simulation results for the trained as well as testing inputs is as shown in the Figures 1 (a) and (b) The 90% results for the testing inputs are encouraging and justify the use of ANN for detection of the disease (a) (b) Fig 1: The classification by ANN for the: (a) training and (b) testing patterns Conclusion We have determined various parameters by processing the holographic images of healthy as well as infected RBCs We have used Artificial Neural Network (ANN) for the detection of malaria infected RBCs In the proposed techniques for the detection of malaria infected RBCs done using ANN gives results almost from % These results can be refined more by increasing the number of parameters and also the sample size of the data provided Acknowledgement: The work is supported by RCC-MSU (RCC/Dir/015/177) Research fund
13 References: [1] [] [3] [4] [5] [6] AAnand VKChhaniwal NRPatel BJavidi Automatic identification of malaria infected RBC with Digital Holographic Microscope Using correlation algorithm IEEE photonic journal vol 4 no G Cybenko Approximation by superposition id sigmoidal functions Mathematics of control signals and systems vol no S Haykin Neural network and learning machines Phi Learning Pvt Ltd 010 S Hornik H White Multi-layer feed-forward networks are universal approximators Neural Networks vol J M Zurada Introduction to Artificial Neural system Jaico publishing house 004 U Schnars Werner P O Juptner Digital Recording and Numerical Reconstruction of Holograms Bremer Institut fur Angewandte Strahltechnik (BIAS) Germeny 00
Detection of Malarial Parasite in Blood Images by two classification Methods: Support Vector Machine (SVM) and Artificial Neural Network (ANN)
Int. J. of Comp. & Info. Tech., (2017) 5(2): 81-92. ISBN: 2345-3877 www.ijocit.org Volume 5, Issue 2 Review Paper Detection of Malarial Parasite in Blood Images by two classification Methods: Support Vector
More informationHolography. How is that different than photography? How is it accomplished? Amplitude & Phase
Holography 1948: Dennis Gabor proposes lensless imaging: wavefront reconstruction. Calls it total recording or Holo gram Concept: record and recreate wavefront incident on film. Amplitude & Phase How is
More informationDigitalna Holografija i Primjene
Digitalna Holografija i Primjene Hrvoje Skenderović Institut za fiziku 5. PIF Radionica, IRB, 16.12.2014. Holography Dennis Gabor invented holography in 1948 as a method for recording and reconstructing
More informationAutomated Disease Identification With 3-D Optical Imaging: A Medical
Automated Disease Identification With 3-D Optical Imaging: A Medical Diagnostic Tool This paper provides an overview of the development of compact digital holographic microscopes and their applications
More informationCOMPARISION OF REGRESSION WITH NEURAL NETWORK MODEL FOR THE VARIATION OF VANISHING POINT WITH VIEW ANGLE IN DEPTH ESTIMATION WITH VARYING BRIGHTNESS
International Journal of Advanced Trends in Computer Science and Engineering, Vol.2, No.1, Pages : 171-177 (2013) COMPARISION OF REGRESSION WITH NEURAL NETWORK MODEL FOR THE VARIATION OF VANISHING POINT
More information6. NEURAL NETWORK BASED PATH PLANNING ALGORITHM 6.1 INTRODUCTION
6 NEURAL NETWORK BASED PATH PLANNING ALGORITHM 61 INTRODUCTION In previous chapters path planning algorithms such as trigonometry based path planning algorithm and direction based path planning algorithm
More informationReview on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,
More informationHolography & Coherence For Holography need coherent beams Two waves coherent if fixed phase relationship between them for some period of time
Holography & Coherence For Holography need coherent beams Two waves coherent if fixed phase relationship between them for some period of time Coherence Coherence appear in two ways Spatial Coherence Waves
More informationTutorial Solutions. 10 Holographic Applications Holographic Zone-Plate
10 Holographic Applications 10.1 Holographic Zone-Plate Tutorial Solutions Show that if the intensity pattern for on on-axis holographic lens is recorded in lithographic film, then a one-plate results.
More informationMultilayer Feed-forward networks
Multi Feed-forward networks 1. Computational models of McCulloch and Pitts proposed a binary threshold unit as a computational model for artificial neuron. This first type of neuron has been generalized
More informationHOLOEYE Photonics. HOLOEYE Photonics AG. HOLOEYE Corporation
HOLOEYE Photonics Products and services in the field of diffractive micro-optics Spatial Light Modulator (SLM) for the industrial research R&D in the field of diffractive optics Micro-display technologies
More informationTraffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers
Traffic Signs Recognition using HP and HOG Descriptors Combined to MLP and SVM Classifiers A. Salhi, B. Minaoui, M. Fakir, H. Chakib, H. Grimech Faculty of science and Technology Sultan Moulay Slimane
More informationImage Compression: An Artificial Neural Network Approach
Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and
More informationCOMPUTATIONAL INTELLIGENCE
COMPUTATIONAL INTELLIGENCE Fundamentals Adrian Horzyk Preface Before we can proceed to discuss specific complex methods we have to introduce basic concepts, principles, and models of computational intelligence
More informationExploiting scattering media for exploring 3D objects
Exploiting scattering media for exploring 3D objects Alok Kumar Singh 1, Dinesh N Naik 1,, Giancarlo Pedrini 1, Mitsuo Takeda 1, 3 and Wolfgang Osten 1 1 Institut für Technische Optik and Stuttgart Research
More informationNeural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani
Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer
More informationSIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS
SIMULATION AND VISUALIZATION IN THE EDUCATION OF COHERENT OPTICS J. KORNIS, P. PACHER Department of Physics Technical University of Budapest H-1111 Budafoki út 8., Hungary e-mail: kornis@phy.bme.hu, pacher@phy.bme.hu
More informationNeural Networks. Neural Network. Neural Network. Neural Network 2/21/2008. Andrew Kusiak. Intelligent Systems Laboratory Seamans Center
Neural Networks Neural Network Input Andrew Kusiak Intelligent t Systems Laboratory 2139 Seamans Center Iowa City, IA 52242-1527 andrew-kusiak@uiowa.edu http://www.icaen.uiowa.edu/~ankusiak Tel. 319-335
More informationUsing a multipoint interferometer to measure the orbital angular momentum of light
CHAPTER 3 Using a multipoint interferometer to measure the orbital angular momentum of light Recently it was shown that the orbital angular momentum of light can be measured using a multipoint interferometer,
More informationCoupling of surface roughness to the performance of computer-generated holograms
Coupling of surface roughness to the performance of computer-generated holograms Ping Zhou* and Jim Burge College of Optical Sciences, University of Arizona, Tucson, Arizona 85721, USA *Corresponding author:
More informationAn Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting.
An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. Mohammad Mahmudul Alam Mia, Shovasis Kumar Biswas, Monalisa Chowdhury Urmi, Abubakar
More informationChapter 2: Wave Optics
Chapter : Wave Optics P-1. We can write a plane wave with the z axis taken in the direction of the wave vector k as u(,) r t Acos tkzarg( A) As c /, T 1/ and k / we can rewrite the plane wave as t z u(,)
More informationAssignment # 5. Farrukh Jabeen Due Date: November 2, Neural Networks: Backpropation
Farrukh Jabeen Due Date: November 2, 2009. Neural Networks: Backpropation Assignment # 5 The "Backpropagation" method is one of the most popular methods of "learning" by a neural network. Read the class
More informationFresnel and Fourier digital holography architectures: a comparison.
Fresnel and Fourier digital holography architectures: a comparison. Damien P., David S. Monaghan, Nitesh Pandey, Bryan M. Hennelly. Department of Computer Science, National University of Ireland, Maynooth,
More informationQUANTITATIVE PHASE IMAGING OF BIOLOGICAL CELLS USING OFF-AXIS METHOD OF WIDE FIELD DIGITAL INTERFERENCE MICROSCOPY (WFDIM)
http:// QUANTITATIVE PHASE IMAGING OF BIOLOGICAL CELLS USING OFF-AXIS METHOD OF WIDE FIELD DIGITAL INTERFERENCE MICROSCOPY (WFDIM) Pradeep Kumar Behera 1, Dalip Singh Mehta 2 1,2 Physics,Indian Institute
More informationCharacter Recognition Using Convolutional Neural Networks
Character Recognition Using Convolutional Neural Networks David Bouchain Seminar Statistical Learning Theory University of Ulm, Germany Institute for Neural Information Processing Winter 2006/2007 Abstract
More informationEdge Detection for Dental X-ray Image Segmentation using Neural Network approach
Volume 1, No. 7, September 2012 ISSN 2278-1080 The International Journal of Computer Science & Applications (TIJCSA) RESEARCH PAPER Available Online at http://www.journalofcomputerscience.com/ Edge Detection
More informationSimple, complete, and novel quantitative model of holography for students of science and science education
Journal of Physics: Conference Series Simple, complete, and novel quantitative model of holography for students of science and science education To cite this article: Dale W Olson 2013 J. Phys.: Conf.
More informationLaser sensors. Transmitter. Receiver. Basilio Bona ROBOTICA 03CFIOR
Mobile & Service Robotics Sensors for Robotics 3 Laser sensors Rays are transmitted and received coaxially The target is illuminated by collimated rays The receiver measures the time of flight (back and
More informationChapter 37. Wave Optics
Chapter 37 Wave Optics Wave Optics Wave optics is a study concerned with phenomena that cannot be adequately explained by geometric (ray) optics. Sometimes called physical optics These phenomena include:
More informationspecular diffuse reflection.
Lesson 8 Light and Optics The Nature of Light Properties of Light: Reflection Refraction Interference Diffraction Polarization Dispersion and Prisms Total Internal Reflection Huygens s Principle The Nature
More informationHolography 24th October 2005
24th October 2005 Contents 1 Introduction 4 2 Wavefront Reconstruction 4 2.1 Recording Amplitude and Phase................. 4 2.2 The Recording Medium...................... 6 2.2.1 Amplitude Transmittance
More informationAberrations in Holography
Aberrations in Holography D Padiyar, J Padiyar 1070 Commerce St suite A, San Marcos, CA 92078 dinesh@triple-take.com joy@triple-take.com Abstract. The Seidel aberrations are described as they apply to
More informationE x Direction of Propagation. y B y
x E x Direction of Propagation k z z y B y An electromagnetic wave is a travelling wave which has time varying electric and magnetic fields which are perpendicular to each other and the direction of propagation,
More informationMeasurements of the characteristics of spray droplets using in-line digital particle holography
Journal of Mechanical Science and Technology 3 (9) 67~679 Journal of Mechanical Science and Technology www.springerlink.com/content/738-494x DOI.7/s6-9-47- Measurements of the characteristics of spray
More information16. Holography. Dennis Gabor (1947) Nobel Prize in Physics (1971)
16. Holography Dennis Gabor (1947) Nobel Prize in Physics (1971) Photography Records intensity distribution of light. Does not record direction. Two-dimensional image. Holography = whole + writing Records
More informationBlood Microscopic Image Analysis for Acute Leukemia Detection
I J C T A, 9(9), 2016, pp. 3731-3735 International Science Press Blood Microscopic Image Analysis for Acute Leukemia Detection V. Renuga, J. Sivaraman, S. Vinuraj Kumar, S. Sathish, P. Padmapriya and R.
More informationPHYSICS. Chapter 33 Lecture FOR SCIENTISTS AND ENGINEERS A STRATEGIC APPROACH 4/E RANDALL D. KNIGHT
PHYSICS FOR SCIENTISTS AND ENGINEERS A STRATEGIC APPROACH 4/E Chapter 33 Lecture RANDALL D. KNIGHT Chapter 33 Wave Optics IN THIS CHAPTER, you will learn about and apply the wave model of light. Slide
More informationSupervised Learning in Neural Networks (Part 2)
Supervised Learning in Neural Networks (Part 2) Multilayer neural networks (back-propagation training algorithm) The input signals are propagated in a forward direction on a layer-bylayer basis. Learning
More informationOperation of machine vision system
ROBOT VISION Introduction The process of extracting, characterizing and interpreting information from images. Potential application in many industrial operation. Selection from a bin or conveyer, parts
More informationRobust Detection for Red Blood Cells in Thin Blood Smear Microscopy Using Deep Learning
Robust Detection for Red Blood Cells in Thin Blood Smear Microscopy Using Deep Learning By Yasmin Kassim PhD Candidate in University of Missouri-Columbia Supervised by Dr. Kannappan Palaniappan Mentored
More informationData Mining. Neural Networks
Data Mining Neural Networks Goals for this Unit Basic understanding of Neural Networks and how they work Ability to use Neural Networks to solve real problems Understand when neural networks may be most
More informationChapter 37. Interference of Light Waves
Chapter 37 Interference of Light Waves Wave Optics Wave optics is a study concerned with phenomena that cannot be adequately explained by geometric (ray) optics These phenomena include: Interference Diffraction
More informationCOHERENCE AND INTERFERENCE
COHERENCE AND INTERFERENCE - An interference experiment makes use of coherent waves. The phase shift (Δφ tot ) between the two coherent waves that interfere at any point of screen (where one observes the
More informationReduction of reconstructed particle elongation using iterative min-max filtering in holographic particle image velocimetry
Reduction of reconstructed particle elongation using iterative min-max filtering in holographic particle image velocimetry Yohsuke Tanaka 1, *, Shigeru Murata 1 1: Department of Mechanical System Engineering,
More informationMEASUREMENT OF THE WAVELENGTH WITH APPLICATION OF A DIFFRACTION GRATING AND A SPECTROMETER
Warsaw University of Technology Faculty of Physics Physics Laboratory I P Irma Śledzińska 4 MEASUREMENT OF THE WAVELENGTH WITH APPLICATION OF A DIFFRACTION GRATING AND A SPECTROMETER 1. Fundamentals Electromagnetic
More informationDistortion Correction for Conical Multiplex Holography Using Direct Object-Image Relationship
Proc. Natl. Sci. Counc. ROC(A) Vol. 25, No. 5, 2001. pp. 300-308 Distortion Correction for Conical Multiplex Holography Using Direct Object-Image Relationship YIH-SHYANG CHENG, RAY-CHENG CHANG, AND SHIH-YU
More informationf. (5.3.1) So, the higher frequency means the lower wavelength. Visible part of light spectrum covers the range of wavelengths from
Lecture 5-3 Interference and Diffraction of EM Waves During our previous lectures we have been talking about electromagnetic (EM) waves. As we know, harmonic waves of any type represent periodic process
More informationThe Analysis of Traffic of IP Packets using CGH. Self Organizing Map
2015 International Conference on Computational Science and Computational Intelligence The Analysis of Traffic of IP Packets using CGH Self Organizing Maps Hiroshi Dozono Department of Advanced Fusion Saga
More informationCOMPUTATIONAL AND EXPERIMENTAL INTERFEROMETRIC ANALYSIS OF A CONE-CYLINDER-FLARE BODY. Abstract. I. Introduction
COMPUTATIONAL AND EXPERIMENTAL INTERFEROMETRIC ANALYSIS OF A CONE-CYLINDER-FLARE BODY John R. Cipolla 709 West Homeway Loop, Citrus Springs FL 34434 Abstract A series of computational fluid dynamic (CFD)
More informationManual Diffraction. Manual remote experiment Project e-xperimenteren+ J. Snellenburg, J.M.Mulder
Manual remote experiment Project e-xperimenteren+ J. Snellenburg, J.M.Mulder 30-01-006 Colofon Manual diffraction Manual remote experiment Project e-xperimenteren+ Stichting Digitale Universiteit Oudenoord
More informationRadial Basis Function (RBF) Neural Networks Based on the Triple Modular Redundancy Technology (TMR)
Radial Basis Function (RBF) Neural Networks Based on the Triple Modular Redundancy Technology (TMR) Yaobin Qin qinxx143@umn.edu Supervisor: Pro.lilja Department of Electrical and Computer Engineering Abstract
More informationLab2: Single Photon Interference
Lab2: Single Photon Interference Xiaoshu Chen* Department of Mechanical Engineering, University of Rochester, NY, 14623 ABSTRACT The wave-particle duality of light was verified by multi and single photon
More informationPattern Classification Algorithms for Face Recognition
Chapter 7 Pattern Classification Algorithms for Face Recognition 7.1 Introduction The best pattern recognizers in most instances are human beings. Yet we do not completely understand how the brain recognize
More informationInvited Paper. Nukui-Kitamachi, Koganei, Tokyo, , Japan ABSTRACT 1. INTRODUCTION
Invited Paper Wavefront printing technique with overlapping approach toward high definition holographic image reconstruction K. Wakunami* a, R. Oi a, T. Senoh a, H. Sasaki a, Y. Ichihashi a, K. Yamamoto
More informationCompact, common path quantitative phase microscopic techniques for imaging cell dynamics
PRAMANA c Indian Academy of Sciences Vol. 82, No. 1 journal of January 2014 physics pp. 71 78 Compact, common path quantitative phase microscopic techniques for imaging cell dynamics A ANAND 1,,PVORA 1,
More informationFourier analysis of low-resolution satellite images of cloud
New Zealand Journal of Geology and Geophysics, 1991, Vol. 34: 549-553 0028-8306/91/3404-0549 $2.50/0 Crown copyright 1991 549 Note Fourier analysis of low-resolution satellite images of cloud S. G. BRADLEY
More informationDraft SPOTS Standard Part III (7)
SPOTS Good Practice Guide to Electronic Speckle Pattern Interferometry for Displacement / Strain Analysis Draft SPOTS Standard Part III (7) CALIBRATION AND ASSESSMENT OF OPTICAL STRAIN MEASUREMENTS Good
More informationCMPT 882 Week 3 Summary
CMPT 882 Week 3 Summary! Artificial Neural Networks (ANNs) are networks of interconnected simple units that are based on a greatly simplified model of the brain. ANNs are useful learning tools by being
More informationWeek 3: Perceptron and Multi-layer Perceptron
Week 3: Perceptron and Multi-layer Perceptron Phong Le, Willem Zuidema November 12, 2013 Last week we studied two famous biological neuron models, Fitzhugh-Nagumo model and Izhikevich model. This week,
More informationIntroduction to Computer-Based Holography
Mitglied der Helmholtz-Gemeinschaft Introduction to Computer-Based Holography October 29, 2013 Carsten Karbach, Jülich Supercomputing Centre (JSC) Why computergenerated holography? Applications Source:
More informationZero Order Correction of Shift-multiplexed Computer Generated Fourier Holograms Recorded in Incoherent Projection Scheme
VII International Conference on Photonics and Information Optics Volume 2018 Conference Paper Zero Order Correction of Shift-multiplexed Computer Generated Fourier Holograms Recorded in Incoherent Projection
More informationNEAR-IR BROADBAND POLARIZER DESIGN BASED ON PHOTONIC CRYSTALS
U.P.B. Sci. Bull., Series A, Vol. 77, Iss. 3, 2015 ISSN 1223-7027 NEAR-IR BROADBAND POLARIZER DESIGN BASED ON PHOTONIC CRYSTALS Bogdan Stefaniţă CALIN 1, Liliana PREDA 2 We have successfully designed a
More informationDIFFRACTION 4.1 DIFFRACTION Difference between Interference and Diffraction Classification Of Diffraction Phenomena
4.1 DIFFRACTION Suppose a light wave incident on a slit AB of sufficient width b, as shown in Figure 1. According to concept of rectilinear propagation of light the region A B on the screen should be uniformly
More informationFACE RECOGNITION USING INDEPENDENT COMPONENT
Chapter 5 FACE RECOGNITION USING INDEPENDENT COMPONENT ANALYSIS OF GABORJET (GABORJET-ICA) 5.1 INTRODUCTION PCA is probably the most widely used subspace projection technique for face recognition. A major
More informationCoherent Gradient Sensing Microscopy: Microinterferometric Technique. for Quantitative Cell Detection
Coherent Gradient Sensing Microscopy: Microinterferometric Technique for Quantitative Cell Detection Proceedings of the SEM Annual Conference June 7-10, 010 Indianapolis, Indiana USA 010 Society for Experimental
More informationChapter 35 &36 Physical Optics
Chapter 35 &36 Physical Optics Physical Optics Phase Difference & Coherence Thin Film Interference 2-Slit Interference Single Slit Interference Diffraction Patterns Diffraction Grating Diffraction & Resolution
More information(Refer Slide Time: 00:10)
Fundamentals of optical and scanning electron microscopy Dr. S. Sankaran Department of Metallurgical and Materials Engineering Indian Institute of Technology, Madras Module 02 Unit-4 Phase contrast, Polarized
More informationInstantaneously trained neural networks with complex inputs
Louisiana State University LSU Digital Commons LSU Master's Theses Graduate School 2003 Instantaneously trained neural networks with complex inputs Pritam Rajagopal Louisiana State University and Agricultural
More informationTRUE 3D DIGITAL HOLOGRAPHIC TOMOGRAPHY FOR VIRTUAL REALITY APPLICATIONS. Thesis. Submitted to. The School of Engineering of the UNIVERSITY OF DAYTON
TRUE 3D DIGITAL HOLOGRAPHIC TOMOGRAPHY FOR VIRTUAL REALITY APPLICATIONS Thesis Submitted to The School of Engineering of the UNIVERSITY OF DAYTON In Partial Fulfillment of the Requirements for The Degree
More informationTo determine the wavelength of laser light using single slit diffraction
9 To determine the wavelength of laser light using single slit diffraction pattern 91 Apparatus: Helium-Neon laser or diode laser, a single slit with adjustable aperture width, optical detector and power
More informationOPTI-521 Graduate Report 2 Matthew Risi Tutorial: Introduction to imaging, and estimate of image quality degradation from optical surfaces
OPTI-521 Graduate Report 2 Matthew Risi Tutorial: Introduction to imaging, and estimate of image quality degradation from optical surfaces Abstract The purpose of this tutorial is to introduce the concept
More informationDigital correlation hologram implemented on optical correlator
Digital correlation hologram implemented on optical correlator David Abookasis and Joseph Rosen Ben-Gurion University of the Negev Department of Electrical and Computer Engineering P. O. Box 653, Beer-Sheva
More informationExperiment 8 Wave Optics
Physics 263 Experiment 8 Wave Optics In this laboratory, we will perform two experiments on wave optics. 1 Double Slit Interference In two-slit interference, light falls on an opaque screen with two closely
More informationDynamic Analysis of Structures Using Neural Networks
Dynamic Analysis of Structures Using Neural Networks Alireza Lavaei Academic member, Islamic Azad University, Boroujerd Branch, Iran Alireza Lohrasbi Academic member, Islamic Azad University, Boroujerd
More informationFourier, Fresnel and Image CGHs of three-dimensional objects observed from many different projections
Fourier, Fresnel and Image CGHs of three-dimensional objects observed from many different projections David Abookasis and Joseph Rosen Ben-Gurion University of the Negev Department of Electrical and Computer
More informationNeural Network and Deep Learning. Donglin Zeng, Department of Biostatistics, University of North Carolina
Neural Network and Deep Learning Early history of deep learning Deep learning dates back to 1940s: known as cybernetics in the 1940s-60s, connectionism in the 1980s-90s, and under the current name starting
More informationMeasurements using three-dimensional product imaging
ARCHIVES of FOUNDRY ENGINEERING Published quarterly as the organ of the Foundry Commission of the Polish Academy of Sciences ISSN (1897-3310) Volume 10 Special Issue 3/2010 41 46 7/3 Measurements using
More informationISSN: ISO 9001:2008 Certified International Journal of Engineering and Innovative Technology (IJEIT) Volume 3, Issue 1, July 2013
Application of Neural Network for Different Learning Parameter in Classification of Local Feature Image Annie anak Joseph, Chong Yung Fook Universiti Malaysia Sarawak, Faculty of Engineering, 94300, Kota
More informationBasic optics. Geometrical optics and images Interference Diffraction Diffraction integral. we use simple models that say a lot! more rigorous approach
Basic optics Geometrical optics and images Interference Diffraction Diffraction integral we use simple models that say a lot! more rigorous approach Basic optics Geometrical optics and images Interference
More information2. Neural network basics
2. Neural network basics Next commonalities among different neural networks are discussed in order to get started and show which structural parts or concepts appear in almost all networks. It is presented
More informationClassification of Mammographic Images Using Artificial Neural Networks
Applied Mathematical Sciences, Vol. 7, 2013, no. 89, 4415-4423 HIKARI Ltd, www.m-hikari.com http://dx.doi.org/10.12988/ams.2013.35293 Classification of Mammographic Images Using Artificial Neural Networks
More informationLECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS
LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Neural Networks Classifier Introduction INPUT: classification data, i.e. it contains an classification (class) attribute. WE also say that the class
More informationMu lt i s p e c t r a l
Viewing Angle Analyser Revolutionary system for full spectral and polarization measurement in the entire viewing angle EZContrastMS80 & EZContrastMS88 ADVANCED LIGHT ANALYSIS by Field iris Fourier plane
More informationEdge and local feature detection - 2. Importance of edge detection in computer vision
Edge and local feature detection Gradient based edge detection Edge detection by function fitting Second derivative edge detectors Edge linking and the construction of the chain graph Edge and local feature
More informationFormulas of possible interest
Name: PHYS 3410/6750: Modern Optics Final Exam Thursday 15 December 2011 Prof. Bolton No books, calculators, notes, etc. Formulas of possible interest I = ɛ 0 c E 2 T = 1 2 ɛ 0cE 2 0 E γ = hν γ n = c/v
More informationSynthesis of a multiple-peak spatial degree of coherence for imaging through absorbing media
Synthesis of a multiple-peak spatial degree of coherence for imaging through absorbing media Mark Gokhler and Joseph Rosen The synthesis of a multiple-peak spatial degree of coherence is demonstrated.
More informationDynamical Theory of X-Ray Diffraction
Dynamical Theory of X-Ray Diffraction ANDRE AUTHIER Universite P. et M. Curie, Paris OXFORD UNIVERSITY PRESS Contents I Background and basic results 1 1 Historical developments 3 1.1 Prologue 3 1.2 The
More informationScattering/Wave Terminology A few terms show up throughout the discussion of electron microscopy:
1. Scattering and Diffraction Scattering/Wave Terology A few terms show up throughout the discussion of electron microscopy: First, what do we mean by the terms elastic and inelastic? These are both related
More informationChapter 36. Image Formation
Chapter 36 Image Formation Apr 22, 2012 Light from distant things We learn about a distant thing from the light it generates or redirects. The lenses in our eyes create images of objects our brains can
More informationLAGRANGIAN PARTICLE TRACKING IN ISOTROPIC TURBULENT FLOW VIA HOLOGRAPHIC AND INTENSITY BASED STEREOSCOPY. By Kamran Arjomand
LAGRANGIAN PARTICLE TRACKING IN ISOTROPIC TURBULENT FLOW VIA HOLOGRAPHIC AND INTENSITY BASED STEREOSCOPY By Kamran Arjomand I. Background A. Holographic Imaging 1. Acquire Hologram 3. Numerical Reconstruction
More informationSingle Photon Interference Christopher Marsh Jaime Vela
Single Photon Interference Christopher Marsh Jaime Vela Abstract The purpose of this experiment was to study the dual wave-particle nature of light. Using a Mach-Zehnder and double slit interferometer,
More information11/14/2010 Intelligent Systems and Soft Computing 1
Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in
More informationRange Sensors (time of flight) (1)
Range Sensors (time of flight) (1) Large range distance measurement -> called range sensors Range information: key element for localization and environment modeling Ultrasonic sensors, infra-red sensors
More informationKeywords: ANN; network topology; bathymetric model; representability.
Proceedings of ninth International Conference on Hydro-Science and Engineering (ICHE 2010), IIT Proceedings Madras, Chennai, of ICHE2010, India. IIT Madras, Aug 2-5,2010 DETERMINATION OF 2 NETWORK - 5
More informationA Review on Plant Disease Detection using Image Processing
A Review on Plant Disease Detection using Image Processing Tejashri jadhav 1, Neha Chavan 2, Shital jadhav 3, Vishakha Dubhele 4 1,2,3,4BE Student, Dept. of Electronic & Telecommunication Engineering,
More informationINTERFERENCE. where, m = 0, 1, 2,... (1.2) otherwise, if it is half integral multiple of wavelength, the interference would be destructive.
1.1 INTERFERENCE When two (or more than two) waves of the same frequency travel almost in the same direction and have a phase difference that remains constant with time, the resultant intensity of light
More informationTwo slit interference - Prelab questions
Two slit interference - Prelab questions 1. Show that the intensity distribution given in equation 3 leads to bright and dark fringes at y = mλd/a and y = (m + 1/2) λd/a respectively, where m is an integer.
More informationSimple Spatial Domain Filtering
Simple Spatial Domain Filtering Binary Filters Non-phase-preserving Fourier transform planes Simple phase-step filters (for phase-contrast imaging) Amplitude inverse filters, related to apodization Contrast
More informationPart 7 Holography. Basic Hologram Setup
Part 7 Holography Basic Holographic Technique Light Sources Recording Materials Holographic Non-Destructive Testing Real-Time Double-Exposure Time-Average 2000 - James C. Wyant Part 7 Page 1 of 28 Basic
More information